INDEX

Explanations

various forms of the word "this" and related demonstrative terms in different contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 scor

-0.16

bah

-0.16

angelo

-0.15

agraph

-0.15

angered

-0.14

inge

-0.14

èº«

-0.14

vas

-0.14

icone

-0.14

igar

-0.14

POSITIVE LOGITS

ifar

0.17

ekil

0.16

UPLE

0.16

endas

0.15

auer

0.15

Å¾ÃŃ

0.15

GLISH

0.15

 deflate

0.14

kun

0.14

olem

0.14

Activations Density 0.001%

various forms of the word "this" and related demonstrative terms in different contexts

No Comments

No Known Activations